GTC 2022?? NVIDIA? ????? ??? ?? AI ??????? ????, ??? ?? ??? ?? ???? ???, ?? ???????? ??? ???? ? ?? NVIDIA AI ????? ???? ?? ????? ??????. CEO? Jensen Huang? ???? ?? NVIDIA? ?? ??? ?? ?????.
NVIDIA Riva 2.0? ?????
NVIDIA? ?? Riva 2.0? ??????. Riva? ??, ? ? ??? ??????? ?? ??? ???? ?? ?? ? ???-?-??? ?????? ???? ?? ?? AI SDK???.
?? ??? ??? ????:
- ?? ?? ??? 7? ?? ?? ?? ??
- ?? ??? ???? ??? ?? ???? ???? ??
- TAO Toolkit ? NeMo? ??? ???? ??????
- ????, ????? ? ???? ?????? ??
NVIDIA also announced Riva Enterprise, providing enterprises with large-scale deployments access to speech experts at NVIDIA. Enterprises can try Riva with guided labs on ready to run infrastructure in LaunchPad.
??? NVIDIA? ??? ??? ????? ??? ??? ???? ?? Riva Enterprise? ??????.??? LaunchPad? ???????? ?? ??? ? ?? ???? ?? ?? ???? Riva? ??? ? ? ????.
??? ??? ????? ? GTC ??? ???? ?????:
NVIDIA Merlin 1.0. ?????? ML, CPU, GPU? ??? DL ?? ??? ??
NVIDIA? ??? ???, ?? ??, ??, ??? ? ??? ????? ???? ?????? ????? ?? ? ?? ?????? NVIDIA Merlin 1.0? ??????. ? ?? NVIDIA Merlin ??? ?? ??? ??????? ???? ????? ? ?? ??? ? ??? ???? ? ? ????. ??? ??? ?? ??, ?? ? ?? ??? ?? ???? ???? ???? ??? ??? ????? ?????? ???? ??? ??, ??? ?? ?? ?????? ?????.
?? ??? ??? ????:
- Merlin Models? ??? ???? 50? ??? ??? ?? ??? ???? ? ??? ? ?? ??? ????????.
- ?? ?? ????? ?? ??? ?????? Merlin ???? ??? Triton ???? ???? ????? ?????? ?? ?????.
- ??? ?? GPU, ?? ?? ?? ? ??? ???? ?? ???? ??
?? ???? ?? ? ??? ??? ????, NVIDIA Merlin? ?? ?? ??????.
??? ??? ????? ? GTC ??? ???? ?????:
- Building and Deploying Recommender Systems Quickly and Easily with NVIDIA Merlin (NVIDIA)
- Scaling Real-time Deep Learning Recommendation Inference at a 150M+ User Scale (ShareChat)
- Large-scale Recommendation System on GPU at Life-Service Scenario (Meituan)
- Building Recommender Systems More Easily using Merlin Models (NVIDIA)
NVIDIA Triton? ??? ??
NVIDIA? NVIDIA Triton? ??? ?? ????? ??????. Triton? ?? ?? ?? ??????? ??? ?? ??? AI? ???? ?? ?? ?? ??? ????????.
?? ??? ??? ????:
- Triton FIL ???: ??? ?? CPU ???? ?? ?? ?????(expalinability)?? ??? ??????.
- Kubernetes?? ??? Triton ???? ?? ? ??? ????? ????? ?? Triton ?? ???. ?? ???? 3? ? ??? ?? ????.
- Triton ?? ?????? Triton? ??? ?? ??? ?? ?? ?? ??? ??????.
- ?? ??? ?? Fleet Command ??.
- MLFlow ??? ???? ?? AWS Interiia ? MLFlow ???? ?? ??.
- NVIDIA LaunchPad?? Triton ??? ?? ??? ?? ?? ?? ?? ????? Triton ??? ??? ? ????.
- NGC ?????? Triton? ?????? GitHub?? ??? ??? ???? ? ????.
NGC ?????? Triton? ?????? GitHub?? ??? ??? ???? ? ????.
??? ??? ????? ? GTC ??? ???? ?????:
- Fast, Scalable, and Standardized AI Inference Deployment for Multiple Frameworks, Diverse Models on CPUs and GPUs with Open-source NVIDIA Triton
- Optimal AzureML Triton Model Deployment using the Model Analyzer
NVIDIA NeMo Megatron? ???
NVIDIA? ??? ?? ??(LLM)? ???? ?? ?????? NVIDIA Nemo Megatron? ?? ??? ??????. Nemo Megatron? ?? ?? ??? ??? LLM? ?? ?? ?? ??? ??? ? ????. ?? ?? ?? ?? ??, ??? ??? ???? ? ???? ????? ???? ?? ??? ???? ? ????.
?? ??? ??? ????:
- Hyper parameter tuning tool that automatically creates recipes based on customers’ needs and infrastructure limitations.
- Reference recipes for T5 and mT5 models.
- Cloud support for Azure.
- Distributed data preprocessing scripts to shorten end-to-end training time.
- ??? ??? ???? ??? ?? ???? ???? ???? ??? ???? ?? ?.
- T5 ? mT5 ?? ????
- Azure ???? ??
- ??? ??? ??? ????? ?? ?? ? ?? ?? ?? ??
?? ???? ????? ??? ?????.
??? ??? ????? ? GTC ??? ???? ?????:
- Building Large-scale, Localized Language Models: From Data Preparation to Training and Deployment to Production
- How to Avoid the Staggering Cost of Training State-of-the-art Large Language Models
- Connect with the Experts: Conversational AI: Build Applications with Riva and Train Multibillion Parameter Language Models using Nemo-Megatron
NVIDIA Maxine? ??? ??
NVIDIA? ?? ??? NVIDIA Maxine? ??????. NVIDIA Maxine? GPU ?????? SDK ????, AI? ?? ??? ? ??? ??? ?????, ??? ??? ??? ?? ?? ???? ???? ??? ?????. Maxine? ??? ?? ? ?? ? ?? ?????? ??? ? ?? ??? ??? AI ???, ??? ? ???? ??? ?????.
?? ??? ??? ????:
- ??? ?? ???: ??? ?? ???? 8kHz?? 16kHz?, 16kHz?? 48kHz? ?????? ??? ??? ??? ??????.
- ?? ?? ??: ?? ???????? ??? ?? ???? ??? ???? ??????? ???? ?????. AI ?? ??? ?? ??? ?? ???? ? ???? ??? ?????.
- ??? ??: ??? AI ??? ???? ???? ?? ???? ???? ???? ????? ??? ?????.
- ? ?? ??: ??? AI ??? ???? ???? ??? ???? ???? ??? ???? ???.
?? ?? NVIDIA Maxine? ???????..
??? ??? ????? ? GTC ??? ???? ?????:
- How Zoom Video uses Distributed Model Training in Kubernetes Cluster
- How Avaya’s Real-time Cloud Media Processing Core Maintains Ultra-low Latency with Maxine
- Project Starline: A High-fidelity Telepresence System
- Put Your Body into It! Easy Talent Tracking in Virtual Environments
?? ?? GTC? ???? ?? GPU ?? AI ??? ?? ????? ?????.